Of course we don’t know what is yet in store for the 2017 AP Statistics Exam, but here is a quick recap of the 2016 AP Statistics Exam:

Question #1: Students had to interpret a histogram to describe a distribution. Then one of the values in the distribution was changed, and students were asked to consider what would happen to the mean and median. This is a pretty “typical” question #1 in that students were asked to describe a distribution.

Question #2: Students had to carry out a chi-square test of homogeneity. There was much discussion about whether or not this was a test of homogeneity, or a test of association. Because there are three populations, it is a test of homogeneity. The question was a bit misleading in asking students whether there was evidence of an “association”. The second part of the question asked students to do some follow-up analysis.

Question #3: This question was about experimental design. They were asked to identify explanatory and response variables as well as to explain how one of the variables could be a confounding variable.

Question #4: Most AP Statistics Exams have a question that is the “probability question”. This one fits the bill. Students had to calculate a probability of independent events and then a conditional probability. Finally, they had to interpret the conditional probability (similar to the p-value of a significance test) in order to make a decision.

Question #5: Students had to calculate a confidence interval to estimate a proportion. Then they had to demonstrate an understanding of the conditions necessary to construct such an interval and then explain why a two-sample z-test for proportions was not appropriate.

Question #6: Students had to interpret a scatterplot and then the slope of the line of best fit. The investigative part of the question asked students to consider what happens when the data is disaggregated by another variable. This investigative task is quite similar to many others in that the first parts of the question are well within the curriculum of AP Statistics, while the last part of the question pushes students into new unexplored territory.

Overall, I would say that this test fits the mold of most AP Statistics Exams. In the free response, students can be expected to have to do some one-variable analysis, some two-variable analysis, some probability, some experimental design, a significance test, and a confidence interval. This Exam covered all of these concepts.

Here are my biggest three takeaways from last years exam:

The AP Statistics Exam has a focus on statistical thinking, reasoning, and understanding.

The AP Statistics Exam uses context for every single Free Response question.

The AP Statistics Exam is hard, but with clear expectations.

Of course we don’t know what is yet in store for the 2017 AP Statistics Exam, but here is a quick recap of the 2016 AP Statistics Exam:

Question #1: Students had to interpret a histogram to describe a distribution. Then one of the values in the distribution was changed, and students were asked to consider what would happen to the mean and median. This is a pretty “typical” question #1 in that students were asked to describe a distribution.Question #2:Students had to carry out a chi-square test of homogeneity. There was much discussion about whether or not this was a test of homogeneity, or a test of association. Because there are three populations, it is a test of homogeneity. The question was a bit misleading in asking students whether there was evidence of an “association”. The second part of the question asked students to do some follow-up analysis.Question #3:This question was about experimental design. They were asked to identify explanatory and response variables as well as to explain how one of the variables could be a confounding variable.Question #4:Most AP Statistics Exams have a question that is the “probability question”. This one fits the bill. Students had to calculate a probability of independent events and then a conditional probability. Finally, they had to interpret the conditional probability (similar to the p-value of a significance test) in order to make a decision.Question #5:Students had to calculate a confidence interval to estimate a proportion. Then they had to demonstrate an understanding of the conditions necessary to construct such an interval and then explain why a two-sample z-test for proportions was not appropriate.Question #6:Students had to interpret a scatterplot and then the slope of the line of best fit. The investigative part of the question asked students to consider what happens when the data is disaggregated by another variable. This investigative task is quite similar to many others in that the first parts of the question are well within the curriculum of AP Statistics, while the last part of the question pushes students into new unexplored territory.Overall, I would say that this test fits the mold of most AP Statistics Exams. In the free response, students can be expected to have to do some one-variable analysis, some two-variable analysis, some probability, some experimental design, a significance test, and a confidence interval. This Exam covered all of these concepts.

Here are my biggest three takeaways from last years exam:

For further explanation, see the blog post “The AP Statistics Exam is Doing it Right” at www.thestatsmedic.com

Luke Wilcox